X-Git-Url: http://plrg.eecs.uci.edu/git/?a=blobdiff_plain;f=test%2FCodeGen%2FX86%2Fmemcpy-2.ll;h=0111c0d433f116909691c684762191ede0e6b2f8;hb=c8e72e912627d9276b3cf7c43169d565a0f5a74e;hp=dcc8f0d268c16a74d5835beb6a44f65d92e969cb;hpb=376642ed620ecae05b68c7bc81f79aeb2065abe0;p=oota-llvm.git diff --git a/test/CodeGen/X86/memcpy-2.ll b/test/CodeGen/X86/memcpy-2.ll index dcc8f0d268c..0111c0d433f 100644 --- a/test/CodeGen/X86/memcpy-2.ll +++ b/test/CodeGen/X86/memcpy-2.ll @@ -1,5 +1,5 @@ -; RUN: llc < %s -mattr=+sse2 -mtriple=i686-apple-darwin -mcpu=core2 | FileCheck %s -check-prefix=SSE2 -; RUN: llc < %s -mattr=+sse2 -mtriple=i686-pc-mingw32 -mcpu=core2 | FileCheck %s -check-prefix=SSE2 +; RUN: llc < %s -mattr=+sse2 -mtriple=i686-apple-darwin -mcpu=core2 | FileCheck %s -check-prefix=SSE2-Darwin +; RUN: llc < %s -mattr=+sse2 -mtriple=i686-pc-mingw32 -mcpu=core2 | FileCheck %s -check-prefix=SSE2-Mingw32 ; RUN: llc < %s -mattr=+sse,-sse2 -mtriple=i686-apple-darwin -mcpu=core2 | FileCheck %s -check-prefix=SSE1 ; RUN: llc < %s -mattr=-sse -mtriple=i686-apple-darwin -mcpu=core2 | FileCheck %s -check-prefix=NOSSE ; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=core2 | FileCheck %s -check-prefix=X86-64 @@ -9,21 +9,28 @@ define void @t1(i32 %argc, i8** %argv) nounwind { entry: -; SSE2: t1: -; SSE2: movsd _.str+16, %xmm0 -; SSE2: movsd %xmm0, 16(%esp) -; SSE2: movaps _.str, %xmm0 -; SSE2: movaps %xmm0 -; SSE2: movb $0, 24(%esp) - -; SSE1: t1: -; SSE1: fldl _.str+16 -; SSE1: fstpl 16(%esp) +; SSE2-Darwin-LABEL: t1: +; SSE2-Darwin: movsd _.str+16, %xmm0 +; SSE2-Darwin: movsd %xmm0, 16(%esp) +; SSE2-Darwin: movaps _.str, %xmm0 +; SSE2-Darwin: movaps %xmm0 +; SSE2-Darwin: movb $0, 24(%esp) + +; SSE2-Mingw32-LABEL: t1: +; SSE2-Mingw32: movsd _.str+16, %xmm0 +; SSE2-Mingw32: movsd %xmm0, 16(%esp) +; SSE2-Mingw32: movaps _.str, %xmm0 +; SSE2-Mingw32: movups %xmm0 +; SSE2-Mingw32: movb $0, 24(%esp) + +; SSE1-LABEL: t1: ; SSE1: movaps _.str, %xmm0 ; SSE1: movaps %xmm0 ; SSE1: movb $0, 24(%esp) +; SSE1: movl $0, 20(%esp) +; SSE1: movl $0, 16(%esp) -; NOSSE: t1: +; NOSSE-LABEL: t1: ; NOSSE: movb $0 ; NOSSE: movl $0 ; NOSSE: movl $0 @@ -32,14 +39,14 @@ entry: ; NOSSE: movl $101 ; NOSSE: movl $1734438249 -; X86-64: t1: +; X86-64-LABEL: t1: ; X86-64: movaps _.str(%rip), %xmm0 ; X86-64: movaps %xmm0 ; X86-64: movb $0 ; X86-64: movq $0 %tmp1 = alloca [25 x i8] %tmp2 = bitcast [25 x i8]* %tmp1 to i8* - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %tmp2, i8* getelementptr inbounds ([25 x i8]* @.str, i32 0, i32 0), i32 25, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %tmp2, i8* getelementptr inbounds ([25 x i8], [25 x i8]* @.str, i32 0, i32 0), i32 25, i32 1, i1 false) unreachable } @@ -48,15 +55,19 @@ entry: define void @t2(%struct.s0* nocapture %a, %struct.s0* nocapture %b) nounwind ssp { entry: -; SSE2: t2: -; SSE2: movaps (%eax), %xmm0 -; SSE2: movaps %xmm0, (%eax) +; SSE2-Darwin-LABEL: t2: +; SSE2-Darwin: movaps (%ecx), %xmm0 +; SSE2-Darwin: movaps %xmm0, (%eax) -; SSE1: t2: -; SSE1: movaps (%eax), %xmm0 +; SSE2-Mingw32-LABEL: t2: +; SSE2-Mingw32: movaps (%ecx), %xmm0 +; SSE2-Mingw32: movaps %xmm0, (%eax) + +; SSE1-LABEL: t2: +; SSE1: movaps (%ecx), %xmm0 ; SSE1: movaps %xmm0, (%eax) -; NOSSE: t2: +; NOSSE-LABEL: t2: ; NOSSE: movl ; NOSSE: movl ; NOSSE: movl @@ -68,7 +79,7 @@ entry: ; NOSSE: movl ; NOSSE: movl -; X86-64: t2: +; X86-64-LABEL: t2: ; X86-64: movaps (%rsi), %xmm0 ; X86-64: movaps %xmm0, (%rdi) %tmp2 = bitcast %struct.s0* %a to i8* ; [#uses=1] @@ -79,13 +90,19 @@ entry: define void @t3(%struct.s0* nocapture %a, %struct.s0* nocapture %b) nounwind ssp { entry: -; SSE2: t3: -; SSE2: movsd (%eax), %xmm0 -; SSE2: movsd 8(%eax), %xmm1 -; SSE2: movsd %xmm1, 8(%eax) -; SSE2: movsd %xmm0, (%eax) - -; SSE1: t3: +; SSE2-Darwin-LABEL: t3: +; SSE2-Darwin: movsd (%ecx), %xmm0 +; SSE2-Darwin: movsd 8(%ecx), %xmm1 +; SSE2-Darwin: movsd %xmm1, 8(%eax) +; SSE2-Darwin: movsd %xmm0, (%eax) + +; SSE2-Mingw32-LABEL: t3: +; SSE2-Mingw32: movsd (%ecx), %xmm0 +; SSE2-Mingw32: movsd 8(%ecx), %xmm1 +; SSE2-Mingw32: movsd %xmm1, 8(%eax) +; SSE2-Mingw32: movsd %xmm0, (%eax) + +; SSE1-LABEL: t3: ; SSE1: movl ; SSE1: movl ; SSE1: movl @@ -97,7 +114,7 @@ entry: ; SSE1: movl ; SSE1: movl -; NOSSE: t3: +; NOSSE-LABEL: t3: ; NOSSE: movl ; NOSSE: movl ; NOSSE: movl @@ -109,7 +126,7 @@ entry: ; NOSSE: movl ; NOSSE: movl -; X86-64: t3: +; X86-64-LABEL: t3: ; X86-64: movq (%rsi), %rax ; X86-64: movq 8(%rsi), %rcx ; X86-64: movq %rcx, 8(%rdi) @@ -122,17 +139,27 @@ entry: define void @t4() nounwind { entry: -; SSE2: t4: -; SSE2: movw $120 -; SSE2: movl $2021161080 -; SSE2: movl $2021161080 -; SSE2: movl $2021161080 -; SSE2: movl $2021161080 -; SSE2: movl $2021161080 -; SSE2: movl $2021161080 -; SSE2: movl $2021161080 - -; SSE1: t4: +; SSE2-Darwin-LABEL: t4: +; SSE2-Darwin: movw $120 +; SSE2-Darwin: movl $2021161080 +; SSE2-Darwin: movl $2021161080 +; SSE2-Darwin: movl $2021161080 +; SSE2-Darwin: movl $2021161080 +; SSE2-Darwin: movl $2021161080 +; SSE2-Darwin: movl $2021161080 +; SSE2-Darwin: movl $2021161080 + +; SSE2-Mingw32-LABEL: t4: +; SSE2-Mingw32: movw $120 +; SSE2-Mingw32: movl $2021161080 +; SSE2-Mingw32: movl $2021161080 +; SSE2-Mingw32: movl $2021161080 +; SSE2-Mingw32: movl $2021161080 +; SSE2-Mingw32: movl $2021161080 +; SSE2-Mingw32: movl $2021161080 +; SSE2-Mingw32: movl $2021161080 + +; SSE1-LABEL: t4: ; SSE1: movw $120 ; SSE1: movl $2021161080 ; SSE1: movl $2021161080 @@ -142,7 +169,7 @@ entry: ; SSE1: movl $2021161080 ; SSE1: movl $2021161080 -; NOSSE: t4: +; NOSSE-LABEL: t4: ; NOSSE: movw $120 ; NOSSE: movl $2021161080 ; NOSSE: movl $2021161080 @@ -152,7 +179,7 @@ entry: ; NOSSE: movl $2021161080 ; NOSSE: movl $2021161080 -; X86-64: t4: +; X86-64-LABEL: t4: ; X86-64: movabsq $8680820740569200760, %rax ; X86-64: movq %rax ; X86-64: movq %rax @@ -161,7 +188,7 @@ entry: ; X86-64: movl $2021161080 %tmp1 = alloca [30 x i8] %tmp2 = bitcast [30 x i8]* %tmp1 to i8* - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %tmp2, i8* getelementptr inbounds ([30 x i8]* @.str2, i32 0, i32 0), i32 30, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %tmp2, i8* getelementptr inbounds ([30 x i8], [30 x i8]* @.str2, i32 0, i32 0), i32 30, i32 1, i1 false) unreachable }